Abstract: Methods and systems for handling speech recognition processing in effectively real-time, via the internet, in order that users do not experience noticeable delays from the start of an exercise until they receive responsive feedback. A user uses a client to access the internet and a server supporting speech recognition processing, e.g., for language learning activities. The user inputs speech to the client, which transmits the user speech to the server in approximate real-time. The server evaluates the user speech in context of the current speech recognition exercise being executed, and provides responsive feedback to the client, again, in approximate real-time, with minimum latency delays. The client upon receiving responsive feedback from the server, displays, or otherwise provides, the feedback to the user.

Abstract: Methods and apparatus for quickly selecting an optimal excitation waveform from a codebook are presented herein. To reduce the number of computations required to choose the optimal codebook vector, a subset of codevectors are selected based upon optimal pulse locations, wherein the subset of codevectors form a subcodebook. Rather than searching the entire codebook, only the entries of the subcodebook are searched.

Abstract: A method for the algebraic codebook search of a speech signal encoder, preferably using the Code Excited Linear Prediction process, in which, in order to calculate coefficients of the triangular matrix of the auto-correlation matrix of the Toeplitz type, a time interval comprising n speech signal samplings is divided into an integral number of tracks t with p possible pulse positions each, and in which the coefficients are stored in a memory grouped in combinations of adjacent tracks, combinations of non-adjacent tracks, combinations of identical tracks, and coefficients of the main diagonals of the auto-correlation matrix.

Abstract: A reduced dimensionality eigenvoice analytical technique is used during training to develop context-dependent acoustic models for allophones. Re-estimation processes are performed to more strongly separate speaker-dependent and speaker-independent components of the speech model. The eigenvoice technique is also used during run time upon the speech of a new speaker. The technique removes individual speaker idiosyncrasies, to produce more universally applicable and robust allophone models. In one embodiment the eigenvoice technique is used to identify the centroid of each speaker, which may then be “subtracted out” of the recognition equation.

Abstract: A system, method and computer program product for performing noise reduction. The system receives a sound signal determined to include speech, then estimates a noise value of the received sound signal. Next, the system subtracts the estimated noise value from the received signal, generates a prediction signal of the result of the subtraction, and sends the generated prediction signal to a speech recognition engine.

Abstract: A system, method and computer program product for performing speech detection. The method first receives a sound signal and determines if the energy value of the sound signal is above a threshold energy value. If the energy level of the signal is above the threshold energy value, the method determines a predictive signal of the received signal, subtracts the predictive signal from the signal, and determines if the result of the subtraction indicates the presence of speech. If it is determined that no presence of speech is indicated, the threshold energy value is set to the energy level of the present received signal. If it is determined that the result of the subtraction indicates the presence of speech, the received signal is sent to a speech recognition engine. The speech recognition engine generates control system commands for controlling one or more system components. The system components are vehicle system components.

Abstract: A voice recognition apparatus and method processes a voice audio stream. As sounds in the voice audio stream are identified that correspond to defined words, the voice recognition system writes the text for the words to an output file. If a sound is encountered that is not recognized as a defined word, a visual marker is placed in the output file to mark the location, and a corresponding audio clip is generated and correlated to the visual marker. When the output file is displayed, any sounds not recognized as defined words are represented by an icon that represents an audio clip. If the user cannot determine from the context what the missing word or phrase is, the user may click on the audio icon, which causes the stored audio clip to be played. In this manner a user can dictate into a voice recognition system with complete confidence that any unrecognized words or phrases will be preserved in their original audio format so the user can later listen and enter the missing information into the document.

Abstract: A system and method for verifying user identity, in accordance with the present invention, includes a conversational system for receiving inputs from a user and transforming the inputs into formal commands. A behavior verifier is coupled to the conversational system for extracting features from the inputs. The features include behavior patterns of the user. The behavior verifier is adapted to compare the input behavior to a behavior model to determine if the user is authorized to interact with the system.

Abstract: A word predicting method for use with a voice recognition using a computer includes the steps of specifying a sentence structure of a history up to a word immediately before the word to be predicted, referring to a context tree stored in arboreal context tree storage section having information about possible structures of a sentence and a probability of appearance of words with respect to the structures at nodes, and predicting words based on the context tree and the specified sentence structure of the history.

Abstract: A method for processing speech audio in a network connected client device can include selecting a speech grammar for use in a speech recognition system in the network connected client device; characterizing the selected speech grammar; and, based on the characterization, determining whether to process the speech grammar locally in the network connected client device, or remotely in a speech server in the network. In one aspect of the invention, the selecting step can include establishing a communications session with a speech server; and, querying the speech server for a speech grammar over the established communications session. Additionally, the selecting step can further include registering the speech grammar in the speech recognition system.

Abstract: Television speech is provided in a desired language using closed caption data already present in a received television signal. The closed caption data, which is representative of words, is extracted from the television signal. The closed caption data is then processed in a speech synthesizer to provide said words as speech in a desired language. The closed caption data can be translated from a first language to a second language prior to or concurrently with conversion to speech. Alternatively, the closed caption data can be carried in various languages in the television signal, and the data in the desired language can be selected for extraction from the television signal and conversion to speech.

Abstract: A speech output apparatus is disclosed, which can allow the user to easily catch synthetic speech when the synthetic speech is output upon being superposed on a music output. The apparatus output can output a music and synthetic speech that indicates contents of information such as an e-mail and is superposed on the music. When the synthetic speech is output to be superposed on the music during output, the apparatus gradually decreases a tone volume of the music.

Abstract: In a text-to-speech system, a method of converting text-to-speech can include receiving a text input and comparing the received text input to at least one entry in a text-to-speech cache memory. Each entry in the text-to-speech cache memory can specify a corresponding spoken output. If the text input matches one of the entries in the text-to-speech cache memory, the cached speech output specified by the matching entry can be provided.

Abstract: A system and method is provided that randomly generates text with a given structure. The structure is taken from a number of learning examples. The structure of training examples is captured by word classification and the definition of the relationships between word classes in a given language. The text generated with this procedure is intended to replicate the information given by the original learning examples. The resulting text may be used to better model the structure of a language in a stochastic language model.

Abstract: A voice synthesizing apparatus comprises: a storage device that stores a first database storing a first parameter obtained by analyzing a voice and a second database storing a second parameter obtained by analyzing a voice with vibrato; an input device that inputs information for a voice to be synthesized; a generating device that generates a third parameter based on the first parameter read from the first database and the second parameter read from the second database in accordance with the input information; and a synthesizing device that synthesizes the voice in accordance with the third parameter. A very real vibrato effect can be added to a synthesized voice.

Abstract: Embodiments of the present invention provide method and apparatus for determining audience affinity and/or aptitude in portions of media works and for developing information that represent measures of the audience affinity and/or aptitude. Further embodiments of present invention provide method and apparatus for utilizing the information to create altered media works and/or to present the altered media works to an audience. One embodiment of the present invention is a method for inferring audience affinity or aptitude with regard to content or properties of portions of a media work which includes: (a) presenting the media work to an audience; (b) obtaining user input regarding presentation rates for the portions of the media work; (c) correlating content or properties of the portion with the presentation rates; and; (d) associating audience affinity or aptitude with the correlated content or properties.

Abstract: Disclosed are an auto attendant system and its method and a call forwarding method using a speech recognition. The auto attendant system according to the invention includes first storing unit for storing information on a subscriber, a first call processing unit for receiving a recognizable name of the subscriber to be communicated with from a user to transfer the same to first speech recognizing unit, and searching the information on the subscriber from the first storing unit to connect a call to a destination number of the subscriber based on the searched information on the subscriber, and first speech recognizing unit for transferring the result of the recognized speech to the first call processing unit by recognizing the speech transferred from the first call processing unit.

Abstract: A method of navigating textual information via auditory indicators is provided. Through the pervasive and immediate articulation of virtually all textual elements in response to a comparatively passive action, such as a selection device rollover, a user may quickly peruse titles, headings, list items, and so on, as well as emphasized text, paragraphs, captions, and virtually any unit of visually contiguous text. A user may also hear a particular selected word via a slightly more active action, such as clicking a mouse button. Via use of this method, a child, or other user who may understand a language, but not be able to recognize its orthography, may successfully and easily navigate textual documents. The method also resumes articulation of text that has been stopped due to a passive deindication. The articulation is restarted approximately at the word where it was stopped.

Abstract: The present invention applies speech recognition technology to remote access, verification, and identification applications. Speech recognition is used to raise the security level of many types of transaction systems which previously had serious safety drawbacks, including: point of sale systems, home authorization systems, systems for establishing a call to a called party (including prison telephone systems), internet access systems, web site access systems, systems for obtaining access to protected computer networks, systems for accessing a restricted hyperlink, desktop computer security systems, and systems for gaining access to a networked server. A general speech recognition system using communication is also presented.

Abstract: A method, apparatus and computer program product provide location-specific responses in an automated voice response system. A microphone signal is received from each of a plurality of microphones. The microphones are located within a defined environment. A spoken command is identified utilizing voice recognition responsive to the received microphone signals. A sound origin or sound location vector is identified responsive to each identified spoken command from respective ones of the plurality of microphones. A response command is provided based upon the identified sound location vector.

Abstract: The invention relates to a method for adding an information title containing audio data to a document. It provides a method for rapidly adding audio data to those data stored in a computer (PC or laptop) or PDA (Personal Data Assistant). The invention allows audio data to be recorded by an audio recorder and saved as an audio file after the information title of a document is opened. A link between the opened information title and the audio file is created, and an audio link tag is then shown on the information title linked with the audio data. The audio data can be easily retrieved by clicking the information title.

Abstract: A comprehensive system is provided for designing a voice activated user interface (VA UI) having a semantic and syntactic structure adapted to the culture and conventions of spoken language for the intended users. The system decouples the content dimension of speech (semantics) and the manner-of-speaking dimension (syntax) in a systematic way. By decoupling these dimensions, the VA UI can be optimized with respect to each dimension independently and jointly. The approach is general across languages and encompasses universal variables of language and culture. Also provided are voice activated user interfaces with semantic and syntactic structures so adapted, as well as a prompting grammar and error handling methods adapted to such user interfaces.

Abstract: Gesture and handwriting recognition agents provide possible interpretations of electronic ink. Recognition is performed on both individual strokes and combinations of strokes in the input ink lattice. The interpretations of electronic ink are classified and encoded as symbol complexes where symbols convey specific attributes of the contents of the stroke. The use of symbol complexes to represent strokes in the input ink lattice facilitates reference to sets of entities of a specific type.

Abstract: A comprehensive system is provided for designing a voice activated user interface (VA UI) having a semantic and syntactic structure adapted to the culture and conventions of spoken language for the intended users. The system decouples the content dimension of speech (semantics) and the manner-of-speaking dimension (syntax) in a systematic way. By decoupling these dimensions, the VA UI can be optimized with respect to each dimension independently and jointly. The approach is general across languages and encompasses universal variables of language and culture. Also provided are voice activated user interfaces with semantic and syntactic structures so adapted, as well as a prompting grammar and error handling methods adapted to such user interfaces.

Abstract: A system, method and computer program product are disclosed for generating revenue utilizing a network-based supply chain management framework. Data is received via a network from a plurality of stores of a supply chain. A plurality of users are allowed to access the data utilizing a network-based interface. The users are identified upon accessing the data utilizing the network-based interface so that the users can be charged a fee based on a number of times the users access the data utilizing the network-based interface.

Abstract: A personalized health video system, method and apparatus which comprises the components of: a personal data collecting device, Internet enablement device, information system, video serving device, server operating system, user operating system, graphical creation device, viewing device, audio device, relationship generating device, script generating device, charts generating device, chart reviewing device, and video library device; the components arranged and interconnected and enabled in an operating personalized health video system.

Abstract: A system which allows wireless airtime units to be used as a medium of exchange. For example, with the novel wireless server system, wireless airtime units may be used as a form of currency by a user in exchange for other types of products or services. In addition, the novel system can be used to provide new types of incentives that reward users with airtime wireless units. Thus, wireless airtime units can be awarded to users that view electronic advertisements, visit desired web pages or purchase particular products. Users can in turn, use these wireless airtime units to obtain airtime for their wireless communications devices, or alternatively, to exchange the wireless airtime units for other goods and services.

Abstract: The present invention is a method and apparatus for matching pets, particularly dogs and cats, with an appropriate product by a pet owner. A breed code is assigned to each breed of pet based on predetermined criteria. Pet products and supplies are classified based on the suitability of the product for pets of various breed codes. The breed codes assigned to each breed and breed codes assigned to each product are published and made available to the consumer so that a pet owner may make an informed decision in purchasing a product for a pet.

Abstract: Apparatus for determining the output of a contract or agreement at any point in time as required, comprising means for creating a state machine representative of the contract or agreement, at least some of the clauses and/or conditions of the contract or agreement being represented as a respective state variable of the state machine, means for storing the state machine, means for receiving data representative of one or more events relevant to the contract or agreement, determining whether the event changes the state of the state machine and changing the state of the state machine if required. The apparatus of the present invention, can provide the core for licence repository and automated rights management services, making the task of rights decision-making easier and more efficient. A preferred embodiment involves providing an novel digital representation of the contract, the unique aspect of this model being that it is dynamic, in that it accurately captures the sequential characteristics of real contracts.

Abstract: Standard telecommunications devices are used to initiate and complete transfer of funds from a purchaser account to a vendor or seller account. The device is a standard device not dedicated to the payment system. The customer will initially set up an account by accessing a specified telephone number and registering as a user. This permits the customer to then complete any financial transaction with other registered users by using the keypad input function on the device to enter the details of a transaction, the information being electronically transmitted to a central management system. The central management system will then communicate the transaction to the customer's chosen financial institution as an “on-line” transaction. The transaction is completed and funds are transferred to the central management system. The central management system then automatically transfers the funds to the account of a member vendor.

Abstract: The present invention comprises methods, apparatus and articles of manufacture for providing, analyzing and visualizing corporate and corporate relationship information, and for creating financial products and instruments based on corporate and corporate relationship information. Information types such as entities, relationships, selection, groupings, arrangements, view types are provided to enable the user to interactively review, modify and create information.

Abstract: A method and system are provided for compiling a customer profile. A database that includes identification information for customers is maintained. Customers who physically visit a first entity are identified from the information maintained in the database. Some of those customers execute a transaction with the first entity and some of those customers do not execute a transaction with the first entity.

Abstract: Methods, data structures, and systems by which entities can efficiently discover, extend, validate and establish business relationships over a digital network are disclosed. A transitive trust system can be utilized by any number of interconnected entities in which at least two of the entities are capable of sharing information. One or more entity trust lists contain, for at least two of the entities, at least one characteristic. Each characteristic can, for example, describe or pertain to the actual or perceived dependability, reliability and/or credibility of an entity. The system also includes at least one transactional trust list that contains at least one parameter relative to an exchange between at least two of the entities through at least one degree of separation between the entities. The transactional trust list can, for example, be a listing of any type of parameters that define or describe business exchanges within a particular industry segment.

Abstract: A voting system modifies the ranking of the results obtained by a keyword search by combining the ranking obtained using objective relevancy analysis with a number of free and paid votes cast by end-users and advertisers. The system combines objective algorithmic ranking of Web sites with the endorsement or disapproval by the general public of the Internet search engine users (end-users) and the promotional efforts by the advertisers expressed in the form of voting. The users of the present invention, either general users or advertisers, can cast their votes, paid or free, for the URLs of their choices for certain queries to promote the ranking of the targeted URLs. Furthermore, the general users can cast free disapproval votes to express their disapproval for the sites they find less helpful.

Abstract: An apparatus and method are described for conducting spatially-based valuation of property, taking into account the values of neighbouring properties. The method proceeds by analysing a database of properties including details of at least the location and value of the known properties, and the location of the property to be valued. Other characteristics of the properties may be included in the database. Similarity scores for each property compared with each other property are calculated, and used to identify those properties which are comparable to the property to be valued. All the comparable properties within a predetermined distance from the property to be valued are used to calculate the unknown property value.

Abstract: A view restriction method surely blocks a program voluntarily designated by a viewer from view. When a restricted program is designated by the viewer (step S1), receiver identification information for identifying a receiver of a viewer is associated with the restricted program (step S2). View restriction information is broadcasted together with the restricted program in a broadcasting time range of the restricted program (step S3). At the receiver, the view restriction information is captured (step S4). At the receiver, display of the restricted program is restricted if the receiver identification information included in the view restriction information matches that set at the receiver (step S5).

Abstract: Systems and methods for interacting with recipients. The systems can be computer controlled and provide audio and/or textual output to a recipient. In some cases, the audio output is created by accessing an audio file on the system, converting the audio output to an audio signal, and providing the audio output to the recipient. In various cases, a user selects the appropriate output from a subset of possible outputs provided via the system. The methods include various ways for directing a pseudo-conversation with a recipient via a conversation control system.

Abstract: Systems and methods for interacting with recipients. The systems can be computer controlled and provide audio and/or textual output to a recipient. In some cases, the audio output is created by accessing an audio file on the system, converting the audio output to an audio signal, and providing the audio output to the recipient. In various cases, a user selects the appropriate output from a subset of possible outputs provided via the system. The methods include various ways for directing a pseudo-conversation with a recipient via a conversation control system.

Abstract: A method is described that provides a notification to the sender or mailer of a mailpiece when the addressee of the mailpiece has changed address. One step in the method includes creation of an updated delivery code that may comprise both the forwarding address of the addressee, the sender's address information, and corresponding barcodes. The postal delivery system sends the mailed item to the forwarding address and provides the sender with the updated information for the addressee. The notification can occur by electronic message systems or delivery of a physical notification.

Abstract: The present invention disclosed a method for approving expense applications. It is applied in a computer system that has set up a procedure for approving expenses and comprises the following steps: submitting an expense application and personally checking it; entering it into the computer system if the expense application is approved, or returning it for resubmission if it is rejected; following up with a second check by the computer system; saving it on the computer system and creating a ledger for if the application information is approved by the computer system, or returning it for resubmission if it is rejected.

Abstract: The present invention relates to methods of valuing property assets and methods of securitizing such assets. The present invention provides a means whereby holders or owners of proprietary intellectual property may readily determine the value to the business of the securitization of their intellectual property estate and obtain capital by securitizing all or part of their intellectual property estate.

Abstract: A sales system is disclosed capable of effective afterward use of service data once obtained with a customer in a shop. Service members in the shop have their own portable data terminal units 3a to 3c for inputting data corresponding to contents of business talks with customers to form service data satisfying predetermined items. The service data is radio transmitted and stored in a shop computer 1. An initial business talk with a customer visiting the shop may not produce sales, but the service data obtained at that time are stored in a shop computer. The stored service data is made use of for transmitting purchase promotion data to the customer to thereby produce a change of a transaction with the customer.

Abstract: A method of providing medical services comprises assigning trained medical representatives from a central office, who are employed by the central office, to locations remote from the central office, providing medical services to patients by the medical representatives at each location while linked to and under the supervision of a licensed physician and billing each patient for medical services provided to that patient by the medical representative through said licensed physician. The patient, licensed physician or medical representative submits the bill to an insurer for reimbursement. The method fulfills all of the responsibilities, duties and services of a trainer at a school without the school paying for the professional service, thereby eliminating the need and expense of a trainer at a school.

Abstract: With the development of a business that will supply a bonded visitation specialist to visit a patient or confined individual and supply personal caring contact that can make a person feel the much needed connection with family and friends, life can be made more enjoyable and healthy. In addition, with the advent of Internet technology and the latest video and audio recording and conferencing capabilities, these visitations can be made more personal, even if the caring family member is a great distance away. The professional visitation provider is a formal, dependable, unbiased, intermediary service that has been created to give family, friends and confined individual the sense of comfort that communication with a familiar person provides.

Abstract: In a medical information system, an in-hospital server stores patient registration information from a patient registration terminal in a hospital, and medical images related to said patient. A surgery unit server reads out registration information such as the name, the date of birth, and the diagnosis history of the patient having surgery, and medical images related to the patient from the in-hospital server. A first controller reads out medical information on said patient, which is accumulated in the in-hospital server via the surgery unit server by inputting patient information (the name of the patient, ID code) for identifying the patient by an input device, and displays this information on a display device. At this time, in the event that the patient information which is input from the input device does not agree with the patient information which is registered in the in-hospital server, the information to that effect is displayed on a display device.

Abstract: A method for assessing and analyzing one or more drugs, adverse effects and associated risks, and patient characteristics resulting from the use of at least drug of interest is disclosed. The method comprises the steps of selecting one or more cases for analysis, said cases describing the behavior between at least one drug of interest and a patient genotype; profiling statistically derived values from multiple cases related to the safety of the at least one drug, wherein at least one filter is employed for deriving said values; at least one data mining engine; and an output device for displaying the analytic results from the data mining engine. A system for performing the method is likewise disclosed.

Abstract: The present invention discloses methods and systems useful in sorting, tracking and reporting information, for example, information relating to sling procedures for treating incontinence.

Abstract: A system and a method for providing patient medical financial information through a networked aggregate medical server are provided. Patient medical financial information may be received at the server. Patient access instructions may be received at the server. An access request for medical financial information may be received at the server from a requestor. Correspondence with the access request and the patient access instructions may be determined. The medical financial information may be formatted into a requester readable data format that may be integrated into a home accounting or tax software program. A portion of the medical financial information may be sent to the requestor based on the patient access instructions if the access request and the patient instructions correspond.

Abstract: A method and system for healthcare decisionmaking wherein a consumer begins with a diagnosis, is educated on the interpretation of relevant data relating thereto, assess risk, selects and prioritizes search criteria, reviews treatment option results and compares the results based on their preference, or by using statistically valid data derived from consumers like themselves. The method and system presents a structured framework for communicating information that has been personalized and customized to an individual who is a consumer of information about healthcare. The system is a networked, knowledge-based system that assists the consumer in assessing healthcare treatment options for a variety of healthcare conditions, procedures and clinical diagnoses.

Abstract: A method, system, and computer program product for storing and retrieving patient data in a database connected to a network is disclosed. The method, system, and computer program product comprises storing clinical data in the database, extracting data from the clinical data, querying the database using a taxonomy that includes inclusive or exclusive search criterion, and receiving a result set. The method, system, and computer program product comprises creating a taxonomy that includes at least one search criterion, sending a query to the database, the query including said at least one search criteria, receiving the result set in response to the query, the result set including at least one result record, and displaying said at least one result record. The method, system, and computer program product can further include a user such as a clinical researcher, a treating physician, or a consulting physician analyzing the result set.